fix: invalid bytes in character encoding (#46)

### What this PR does? 修复内容中包含非法的 XML 字符导致 RSS 格式异常的问题 ```release-note 修复内容中包含非法的 XML 字符导致 RSS 格式异常的问题 ```
halo-dev · Dec 16, 2024 · 80b1922 · 80b1922
1 parent f6b461d
commit 80b1922
Show file tree

Hide file tree

Showing 2 changed files with 62 additions and 2 deletions.
diff --git a/app/src/main/java/run/halo/feed/RssXmlBuilder.java b/app/src/main/java/run/halo/feed/RssXmlBuilder.java
@@ -7,6 +7,7 @@
 import java.time.ZoneOffset;
 import java.time.format.DateTimeFormatter;
 import java.util.List;
+import java.util.Optional;
 import lombok.extern.slf4j.Slf4j;
 import org.apache.commons.lang3.StringUtils;
 import org.dom4j.Document;
@@ -146,9 +147,13 @@ private void createItemElementsToChannel(Element channel, List<RSS2.Item> items)
 
     private void createItemElementToChannel(Element channel, RSS2.Item item) {
         Element itemElement = channel.addElement("item");
-        itemElement.addElement("title").addCDATA(item.getTitle());
+        itemElement.addElement("title")
+            .addCDATA(XmlCharUtils.removeInvalidXmlChar(item.getTitle()));
         itemElement.addElement("link").addText(item.getLink());
-        var description = getDescriptionWithTelemetry(item);
+
+        var description = Optional.of(getDescriptionWithTelemetry(item))
+            .map(XmlCharUtils::removeInvalidXmlChar)
+            .orElseThrow();
         itemElement.addElement("description").addCDATA(description);
         itemElement.addElement("guid")
             .addAttribute("isPermaLink", "false")

diff --git a/app/src/test/java/run/halo/feed/RSS2Test.java b/app/src/test/java/run/halo/feed/RSS2Test.java
@@ -4,6 +4,7 @@
 
 import java.time.Instant;
 import java.util.Arrays;
+import java.util.Collections;
 import org.junit.jupiter.api.Test;
 
 class RSS2Test {
@@ -130,4 +131,58 @@ void extractRssTagsTest() {
             """.formatted(lastBuildDate);
         assertThat(rssXml).isEqualToIgnoringWhitespace(expected);
     }
+
+    @Test
+    void invalidCharTest() {
+        var rss = RSS2.builder()
+            .title("title")
+            .description("description")
+            .link("link")
+            .items(Collections.singletonList(
+                RSS2.Item.builder()
+                    .title("title1")
+                    .description("""
+                        <p>并且会保留处理后的图片以供后面的访问。</p>
+                        """)
+                    .link("link1")
+                    .pubDate(Instant.EPOCH)
+                    .guid("guid1")
+                    .build()
+            ))
+            .build();
+        var instant = Instant.now();
+        var rssXml = new RssXmlBuilder()
+            .withRss2(rss)
+            .withGenerator("Halo")
+            .withLastBuildDate(instant)
+            .toXmlString();
+
+        var lastBuildDate = RssXmlBuilder.instantToString(instant);
+        // language=xml
+        var expected = """
+            <?xml version="1.0" encoding="UTF-8"?>
+            <rss xmlns:media="http://search.yahoo.com/mrss/" version="2.0">
+            	<channel>
+            		<title>title</title>
+            		<link>link</link>
+            		<description>description</description>
+            		<generator>Halo</generator>
+            		<language>zh-cn</language>
+            		<lastBuildDate>%s</lastBuildDate>
+            		<item>
+            			<title>
+            				<![CDATA[title1]]>
+            			</title>
+            			<link>link1</link>
+            			<description>
+            				<![CDATA[<p>并且会保留处理后的图片以供后面的访问。</p>]]>
+            			</description>
+            			<guid isPermaLink="false">guid1</guid>
+            			<pubDate>Thu, 1 Jan 1970 00:00:00 GMT</pubDate>
+            		</item>
+            	</channel>
+            </rss>
+            """.formatted(lastBuildDate);
+        assertThat(rssXml).isEqualToIgnoringWhitespace(expected);
+    }
 }